Concrete apparent quality detection method based on machine vision

Through machine vision technology and cloud recognition system, combined with manual audit, the problem of inconsistency in manual detection is solved, the efficiency and accuracy of concrete apparent defects are improved, and the automated detection and labeling process is realized.

CN118914190APending Publication Date: 2024-11-08JIANGSU KEXIN ENG TESTING CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310505048.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-08
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing concrete apparent inspection methods rely on manual inspection, and the results are uneven, and the detection personnel are distracted, resulting in some defects not found.

Method used

Using machine vision-based detection methods, concrete surface defects are identified through viewfinders, cloud servers and independent graphics processors, and automatically marked and classified. Combined with manual audits, multi-angle cameras and marking devices are used to mark defect locations.

Benefits of technology

It improves the recognition efficiency and accuracy of concrete apparent defects, reduces the inconsistency of manual inspection and errors caused by diffusion of attention, and realizes an automated detection and labeling process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118914190A_ABST
    Figure CN118914190A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of concrete detection, and discloses a concrete apparent quality detection method based on machine vision, and the method comprises the following steps: carrying out the view finding of the concrete surface condition through a viewfinder; the framing data is uploaded to the cloud storage through the wireless device; identifying the framing data of the cloud storage through the cloud server; carrying out classification identification on the identified file, marking a suspicious place and carrying out manual auditing; sorting the manually audited data, and respectively labeling unqualified parts and qualified parts for storage; receiving the data through a wireless device and downloading the data to a viewfinder; the terminal scans the surface of the concrete again, and marks are made at unqualified positions; the viewfinder comprises a walking frame and a multi-angle camera, and the multi-angle camera is connected with a mobile data storage device in an inserted mode. The invention discloses a concrete apparent quality detection method based on machine vision.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of concrete detection, and in particular to a method for detecting concrete surface quality based on machine vision. Background Art

[0002] Concrete is a general term for engineering composite materials that are made of aggregates bonded together by cementitious materials. The term concrete usually refers to cement as a cementitious material, sand and stone as aggregates, mixed with water in a certain proportion, and then mixed to obtain cement concrete, also known as ordinary concrete. It is widely used in civil engineering. Concrete usually needs to be tested after it has solidified. The method for testing its interior is usually the sound wave transmission method, while the surface is usually tested manually.

[0003] The existing appearance inspection method is usually manual inspection of the appearance. Depending on the concentration of the inspectors, the inspection results are often uneven. After long-term concentration, the inspectors will inevitably become distracted, resulting in obvious defects in some locations not being discovered, which is extremely inconvenient. Therefore, a concrete appearance quality inspection method based on machine vision is proposed to solve the above-mentioned problems. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a method for detecting the apparent quality of concrete based on machine vision, which has the advantage of being able to easily identify the apparent defects of concrete, and solves the problem that the existing apparent detection methods usually require manual detection of the appearance, and the detection results are often uneven depending on the concentration of the detection personnel. Moreover, after long-term concentration, the detection personnel will inevitably become distracted, resulting in obvious defects in some locations often not being discovered, which is extremely inconvenient.

[0006] (II) Technical solution

[0007] The technical solution of the present invention to solve the above technical problem is as follows: A method for detecting the apparent quality of concrete based on machine vision comprises the following steps:

[0008] Step 1. Use the viewfinder to view the concrete surface;

[0009] Step 2, upload the framing data to the cloud storage via wireless devices;

[0010] Step 3, identify the framing data in the cloud storage through the cloud server;

[0011] Step 4: Classify and mark the identified files, and mark suspicious parts for manual review;

[0012] Step 5: Sort out the manually reviewed data and label the unqualified and qualified parts separately for storage;

[0013] Step 6. Receive data through wireless devices and download it to the viewfinder;

[0014] Step 7. The terminal re-scans the concrete surface and marks the unqualified areas;

[0015] The viewfinder includes a walking frame and a multi-angle camera, wherein the multi-angle camera is plugged with a mobile data storage device; the viewfinder also includes a wireless data transceiver fixed to the walking frame and connected to the multi-angle camera;

[0016] The cloud storage and cloud server are implemented based on NAS, and the data is identified through the computing power of NAS;

[0017] The NAS has an independent graphics processor;

[0018] The viewfinder also includes a marking device.

[0019] The beneficial effects of the present invention are:

[0020] The machine vision-based concrete surface quality detection method has the advantage of being able to easily identify the surface defects of concrete.

[0021] Based on the above technical solution, the present invention can also be improved as follows.

[0022] Furthermore, the processing steps of the independent graphics processor are as follows:

[0023] S1. Split the video frame by frame according to the recorded file, and select samples according to the walking speed of the viewfinder to ensure that there is partial overlap between two adjacent samples;

[0024] S2. After the samples are selected, they are manually reviewed to filter out the images with focus failure or poor clarity;

[0025] S3, the independent graphics processor selects samples near the frame again for manual selection to ensure the eligibility of the samples;

[0026] S4, storing all selected samples, and reprocessing them through an independent graphics processor to mark defects;

[0027] S5. For unqualified samples, the independent graphics processor calculates the approximate position parameters through sample comparison and time calculation and records them.

[0028] The beneficial effect of adopting the above further solution is that the overall observation efficiency can be improved through an independent graphics processor.

[0029] Furthermore, the marking device includes a marking frame fixed to the outside of the viewfinder, a spray gun is fixedly arranged on the outside of the marking frame, a plurality of paint boxes are fixedly installed on the outside of the marking frame, and a feed end of the spray gun is connected to a solenoid valve connected to the paint box.

[0030] Furthermore, the colors of the multiple paint boxes are red, yellow and white respectively, and the solenoid valve can be connected to the paint box of a single color by switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the steps of the present invention;

[0032] Figure 2 It is the secondary detection flow chart of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] In an embodiment, a method for detecting the apparent quality of concrete based on machine vision comprises the following steps:

[0035] Step 1. Use the viewfinder to view the concrete surface;

[0036] The viewfinder is recorded via a 720p HD camera and the recorded video is packaged and stored in a removable data storage device using an h.264 encoder.

[0037] Step 2, upload the framing data to the cloud storage via wireless devices;

[0038] In particular, the wireless device automatically connects when it is within a specific local area network, and uploads the data in the mobile data storage to the server via the wireless connection.

[0039] Step 3, identify the framing data in the cloud storage through the cloud server;

[0040] Step 4: Classify and mark the identified files, and mark suspicious parts for manual review;

[0041] Step 5: Sort out the manually reviewed data and label the unqualified and qualified parts separately for storage;

[0042] Step 6. Receive data through wireless devices and download it to the viewfinder;

[0043] Step 7. The terminal re-scans the concrete surface and marks the unqualified areas;

[0044] The viewfinder includes a walking frame and a multi-angle camera, wherein the multi-angle camera is plugged with a mobile data storage device; the viewfinder also includes a wireless data transceiver fixed to the walking frame and connected to the multi-angle camera;

[0045] Cloud storage and cloud servers are implemented based on NAS, and data is identified through the computing power of NAS;

[0046] NAS has an independent graphics processor;

[0047] The viewfinder also includes a marking device.

[0048] The processing steps of the independent graphics processor are as follows:

[0049] S1. Split the video frame by frame according to the recorded file, and select samples according to the walking speed of the viewfinder to ensure that there is partial overlap between two adjacent samples;

[0050] S2. After the samples are selected, they are manually reviewed to filter out the images with focus failure or poor clarity;

[0051] S3, the independent graphics processor selects samples near the frame again for manual selection to ensure the eligibility of the samples;

[0052] S4, storing all selected samples, and reprocessing them through an independent graphics processor to mark defects;

[0053] S5. For unqualified samples, the independent graphics processor calculates the approximate position parameters through sample comparison and time calculation and records them.

[0054] The overall observation efficiency can be improved through an independent graphics processor.

[0055] The marking device comprises a marking frame fixed on the outside of the viewfinder, a spray gun is fixedly arranged on the outside of the marking frame, a plurality of paint boxes are fixedly installed on the outside of the marking frame, and a feed end of the spray gun is connected to a solenoid valve connected to the paint box.

[0056] The colors of the multiple paint boxes are red, yellow and white. The solenoid valve can be connected to the paint box of a single color by switching.

[0057] This method requires two tests on concrete. During the first test, the test can be carried out normally according to this method. After the test is completed, all test results are uniformly tested and registered within a certain working cycle. After the first test result is registered, the viewfinder is used to frame the target position again, and the framing result is compared with the first framing result. Then the difference between the two framing results and the unqualified parts of the first test are marked. In particular, larger defects are marked with red paint, smaller defects are marked with yellow, and the differences are marked with white.

[0058] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0059] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting the apparent quality of concrete based on machine vision, characterized in that: The steps include: Step 1. Use the viewfinder to view the concrete surface; Step 2, upload the framing data to the cloud storage via wireless devices; Step 3, identify the framing data in the cloud storage through the cloud server; Step 4: Classify and mark the identified files, and mark suspicious parts for manual review; Step 5: Sort out the manually reviewed data and label the unqualified and qualified parts separately for storage; Step 6. Receive data through wireless devices and download it to the viewfinder; Step 7. The terminal re-scans the concrete surface and marks the unqualified areas; The viewfinder includes a walking frame and a multi-angle camera, wherein the multi-angle camera is plugged with a mobile data storage device; the viewfinder also includes a wireless data transceiver fixed to the walking frame and connected to the multi-angle camera; The cloud storage and cloud server are implemented based on NAS, and the data is identified through the computing power of NAS; The NAS has an independent graphics processor; The viewfinder also includes a marking device.

2. The method for detecting the apparent quality of concrete based on machine vision according to claim 1, characterized in that: The processing steps of the independent graphics processor are as follows: S1. Split the video frame by frame according to the recorded file, and select samples according to the walking speed of the viewfinder to ensure that there is partial overlap between two adjacent samples; S2. After the samples are selected, they are manually reviewed to filter out the images with focus failure or poor clarity; S3, the independent graphics processor selects samples near the frame again for manual selection to ensure the eligibility of the samples; S4, storing all selected samples, and reprocessing them through an independent graphics processor to mark defects; S5. For unqualified samples, the independent graphics processor calculates the approximate position parameters through sample comparison and time calculation and records them.

3. The method for detecting the apparent quality of concrete based on machine vision according to claim 1, characterized in that: The marking device comprises a marking frame fixed to the outside of the viewfinder, a spray gun is fixedly arranged on the outside of the marking frame, a plurality of paint boxes are fixedly installed on the outside of the marking frame, and a feed end of the spray gun is connected to a solenoid valve connected to the paint box.

4. The method for detecting the apparent quality of concrete based on machine vision according to claim 3 is characterized in that: The colors of the plurality of paint boxes are red, yellow and white respectively, and the solenoid valve can be connected to a paint box of a single color by switching.